Streptococcus pneumoniae is a bacterial pathogen that causes life-threatening infections, including pneumonia and meningitis. These infections are commonly treated with antibiotics, but antibiotics are becoming less effective against S. pneumoniae over time due to changes in the pathogen that cause drug resistance. This phenomenon, called antimicrobial resistance, is resulting in significant healthcare costs and deaths around the world. In a new study, published by Wiley in Advanced Science, researchers used artificial intelligence (AI) to identify approved drugs that may be effective against S. pneumoniae.
Drug repurposing, or the use of drugs with known safety profiles for different purposes, saves time and cost while reducing risk. This process is even more efficient with the use of computational strategies to select promising candidates. AI has been used to predict drugs for repurposing against other pathogens on the World Health Organization (WHO)’s antibiotic development priority list. Now, researchers have used enhanced learning approaches and diverse models to screen a drug library for S. pneumoniae, another of the WHO’s priorities for antimicrobial resistance.
Using a dataset of molecules shown to be active against S. pneumoniae and a larger dataset of molecules inactive against another drug-resistant bacteria, the scientists trained three different learning algorithms: ensembles of decision trees, ensembles of graph neural networks, and ensembles of sequence-based transformers (each previously pre-trained with hundreds of millions of molecules). These different AI models were used to test almost 7,000 candidate drugs for inhibition of S. pneumoniae.
Of these nearly 7,000 candidates, 11 were selected for experimental validation. Nine of the compounds were able to inhibit the growth of S. pneumoniae. One of the two most potent repurposed drugs was effective even against drug-resistant strains of S. pneumoniae. The authors discussed that using three diverse AI models complemented each other in the selection of candidate drugs, making them more efficacious together than individually.
These findings underscore the benefits of using AI models to identify novel drugs and rationally select drugs with the highest potential for repurposing. In a field like antimicrobial resistance, where there is an urgent need for effective compounds, AI-driven computational drug repurposing is a streamlined and affordable strategy with demonstrated success.
Woodlands Hospital in Singapore opened without a legacy system burden and uses one EMR across the patient care journey to support cleaner data, shares deputy CMIO Dr Teresa Wong.
Ambient documentation can return attention to patients and reduce after-hours work, but only when it fits inside the EHR and clinicians measure the full documentation cycle.
Less than a second. That’s how long it takes for an emerging AI tool to detect signs of endometriosis through one simple scan. It’s a much faster process than the current seven-year wait for surgery and less invasive.
The AI tool, called EndoFusion, is a recent development from IMAGENDO, an ongoing collaborative study led by Adelaide University researchers. In this latest study, they found the framework was able to accurately identify two major indicators of advanced endometriosis in pelvic scans, producing the results in just 18 milliseconds.
Researchers say it is a significant development, as MRI and ultrasound imaging are often better at detecting one sign of the condition over the other.
Researchers created a new technique that accurately and rapidly matches X-rays captured during surgery with a patient's preoperative 3D medical scan. This method could make it easier for clinicians to precisely pilot minimally invasive surgical tools, leading to faster and safer procedures.
Clinicians perform many minimally invasive surgeries using real-time X-rays to help them steer devices like catheters and endoscopes through tiny incisions. But since X-rays are flat images, it can be challenging to determine exactly where surgical tools are located and oriented within the patient's body, increasing the risk of complications.
To help localize surgical devices, clinicians may manually align X-rays with preoperative 3D medical images, such as CT scans or MRIs. Artificial intelligence tools designed to streamline this process struggle to align images robustly for all patients, making them infeasible in practice.
This new system, developed by scientists and clinicians at MIT and collaborating institutions, uses an AI model that adapts to each patient in only about five minutes. The model automatically matches one patient's X-rays with 3D scans in a matter of seconds, and with sub-millimeter precision.
Named xvr (which stands for X-ray volume registration), it outperformed existing AI methods by an order of magnitude across a wide range of patients, body parts, and medical procedures.
"A majority of Americans live more than an hour away from a center that can perform noninvasive procedures, like emergency stroke interventions. An hour in stroke time is incredibly substantial. Making these procedures easier by combining 2D and 3D information enables these types of highly specialized life-saving procedures to be more accessible to much broader parts of the population," says Vivek Gopalakrishnan, a postdoc in the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL); a recent graduate of the Harvard-MIT Program in Health Sciences and Technology; and lead author of a paper on xvr, which will appear in Nature.
He is joined on the paper by his advisor Polina Golland, the Sunlin and Priscilla Chou Professor of Electrical Engineering and Computer Science (EECS), a principal investigator in CSAIL, the leader of the Medical Vision Group, and co-senior author of the paper; and Neel Dey, a former postdoc in the Medical Vision Group who is now an investigator at Harvard Medical School and Massachusetts General Hospital as well as co-senior author on the paper. Additional co-authors include David-Dimitris Chlorogiannis, a researcher and clinician at Harvard Medical School; Andrew Abumoussa, a neurosurgeon at St. Luke's Marion Bloch Neuroscience Institute; Anna M. Larson, a pediatric clinician at Shriners Children's Hospital; Nazim Haouchine, an assistant professor of radiology at Harvard and Brigham and Women's Hospital; Darren B. Orbach, a physician and scientist at Boston Children's Hospital; and Sarah Frisken, an associate professor of radiology at Harvard.
Artificial intelligence (AI) tools can help physicians predict treatment and survival outcomes in patients with advanced non-small cell lung cancer (NSCLC) treated with immunotherapy, according to a new study published in Nature Medicine. The study reported findings from the I3LUNG project, a large, international trial aimed at improving the current treatment of metastatic NSCLC by developing AI-based predictive models that can help determine the best therapeutic approach for each individual.
Immunotherapy - a cancer treatment that boosts and uses the power of the patient's immune system against cancer cells - has transformed lung cancer treatment, achieving long-term benefit in 20% to 30% of patients. However, most patients experience resistance to treatment, and physicians still cannot reliably predict which patients will benefit from immunotherapy. Today, treatment decisions rely heavily on the expression of PD-L1 - a biomarker with well-known limitations.
"We need smarter tools," said thoracic oncologist Marina Garassino, MD, Professor of Medicine at UChicago Medicine and senior author of the study.
Better predictive biomarkers could identify which patients are likely to respond to immunotherapy at diagnosis, avoiding unnecessary toxicity and unnecessary cost. Improving the ability to make these predictions can help physicians better tailor treatments for individual patients. The I3LUNG project set out to develop and validate AI tools to support immunotherapy decisions in advanced NSCLC.
For the study, the international research team enrolled 2,396 patients with advanced NSCLC treated with immunotherapy across six centers in Italy, Germany, Greece, Israel, Spain and the United States. For the first phase of the project, the team integrated multiple types of data, including clinical, imaging, pathology, and genomic data, from each patient into a database. They then built and tested two families of AI models trained to predict treatment response and survival using all the collected data.
The researchers found that their AI models consistently outperformed all standard clinical biomarkers. Area Under the Curve, or AUC, is a machine learning metric that quantifies how good an AI model is at classifying information correctly, or in this case, predicting survival outcomes accurately. Scores between 0.8 and 0.9 are considered "excellent." In the I3LUNG study, the AI model that used clinical and blood data achieved an AUC score of 0.77, while the model that incorporated clinical and blood data along with imaging and digital pathology achieved an AU score of 0.88.
Part of the study tested what happens when humans collaborate with the AI tools. Twenty physicians - 10 lung cancer experts and 10 from other specialties - reviewed 100 real patient cases, first without and then with AI support. Access to the AI tool improved sensitivity for identifying responders from an AUC of 0.72 to 0.87. Physicians who were not lung cancer experts showed the greatest improvements, a finding with direct relevance to community oncology settings where thoracic expertise may be limited. Inter-physician agreement rose from slight to moderate, suggesting the tool also promotes more consistent clinical reasoning across different levels of experience.
Chi Mei Medical Center Stroke Center director Dr Hsieh Meng-Tsang explains what separates an AI pilot from deployment and what it takes to scale.
It's well-known that obesity and the cardiometabolic diseases that it can lead to continues to be a major concern among the nation's teens, affecting more than 1 in 5. But while teens and families want to know how to eat healthier, that assistance can be hard to find.
Preventing diabetes by making healthy living tools easily accessible for adolescents is the goal of a new American Diabetes Association (ADA) grant awarded to an investigator at the Jacobs School of Medicine and Biomedical Sciences at the University at Buffalo.
Amanda Ziegler, PhD, research assistant professor in the Primary Care Research Institute in the Department of Family Medicine in the Jacobs School, was awarded a three-year ADA grant titled, "Translating and testing an evidence-based, AI-powered mobile health care model integration into clinical practice for adolescent weight management and diabetes prevention."
Using smartphone technologies that can be readily incorporated into primary care electronic medical systems, along with artificial intelligence-powered support tools, the project is designed to prevent and address adolescent obesity and subsequent cardiometabolic diseases by developing pragmatic approaches for adolescent patients.
"There's a research gap showing that clinicians are sought after for nutrition advice, but they can be apprehensive about discussing it with patients because they either lack confidence or supportive tools for families," says Ziegler, adding that the need to avoid stigmatizing patients can end up making clinicians avoid the topic altogether.
"Our goal is to get information in front of providers and patients in a way that's digestible, not burdensome," she adds. "Our idea is that if all patients get the same initial screening surveys and providers are given patient-specific lifestyle change guidance, then counseling can be more effective and approachable in routine care."
Ziegler's project is an example of implementation science, research designed to more rapidly transition out of the discovery phase and into routine clinical practice, an emphasis of UB's Primary Care Research Institute.
She is partnering with PreventScripts, a mobile health provider that conducts lifestyle screening and treatment to improve cardiometabolic outcomes in adults. The UB project, called PrevenTeen, involves adapting these methods for adolescents, by utilizing community-based participation methods to ensure the program components -- smartphone app, remote monitoring tools, personalized goal setting and clinician-connected support -- are age-appropriate and focused on helping adolescents build healthy eating and lifestyle habits to reduce obesity and future diabetes risk.
Providers face heightened risks, beyond traditional cybersecurity threats, as artificial intelligence proliferates – especially the use of unsanctioned agentic AI by health system employees, a new survey shows.
Artificial intelligence (AI) models prioritize starkly different attributes than humans when making high-stakes decisions, and they don't express indecision like humans do, according to a new study led by Penn State researchers, raising questions about the role of AI in decision support for ethically sensitive situations like medical decisions.
The researchers used a hypothetical scenario to explore AI's moral decision-making in a high-stakes scenario: If there are multiple kidney transplant patients but only one available organ, who should receive the kidney? That's the fundamental question explored by Nobel Laureate Alvin Roth as an example of the challenge of allocating scarce resources. But rather than approaching the problem solely through mechanism design, as Roth did, the team examined how morality influences such decisions.
The researchers compared the judgments of leading large language models with those given by real people in earlier academic studies, investigating where the AI models aligned or misaligned with human values and whether they expressed indecision when faced with difficult ethical trade-offs.
They found that AI chatbots often make decisions that differ from human judgment by oversimplifying complex decisions and expressing unwarranted confidence when there is no clear right answer. They presented their findings at the 2026 Association for Computing Machinery Fairness, Accountability and Transparency (FAccT) conference in June. The study was published in the conference's proceedings.
"Moral decisions in settings like organ allocation directly determine who lives and who dies, so getting AI's role in them right isn't optional," said Hadi Hosseini, associate professor of informatics and intelligent systems and an associate professor of economics at Penn State, who led the study. "While we do not intend to encourage the use of AI as a substitute for professional judgment in medical decision-making or other high-stakes contexts, it's becoming essential to understand their behavior as individuals, organizations and firms more and more rely on AI to make decisions or receive recommendations."
The researchers set up a series of head-to-head comparisons: two hypothetical patients - described by attributes such as age, number of dependents, health status and drinking habits - both in need of the same kidney. They asked several AI chatbots to pick who should receive the kidney, using the same scenarios given to humans - research participants with no specified medical training - in earlier studies.
Researchers at Stanford Medicine have developed two new artificial intelligence models of the biological cell. The first, called universal cell embedding, paved the way for a second-generation model called TranscriptFormer, which has been trained on data from 112 million cells representing 12 species, ranging from single-celled yeast to humans.
The AI cell models make it dramatically easier to compare cells among species - and offer possibilities for new insights on diseases and paths to new cell treatments.
"We're trying to open up a whole new way to think about cell biology," said Stephen Quake, PhD, a professor of bioengineering. He is co-lead author, along with Jure Leskovec, PhD, professor of computer science, and Theo Karaletsos, PhD, of the Chan Zuckerberg Initiative, of two scientific articles about the work, published recently in Nature and Science. "These papers mark the beginning of, we hope, a whole new field and a decade of work," Quake said.
The genome contains the instructions for life, but these days many biologists focus on gene expression - that is, which genes a particular cell is using.
For example, a beta cell in the pancreas expresses the gene for insulin, plus genes related to storage and release of the hormone. The white blood cells known as B cells produce antibodies to fight disease. A cell in your skin, on the other hand, might express genes to make hair or pigment. These differences in expression can be used to tell cell types apart. Healthy and sick cells also have different gene expression patterns, as do cells from different species.
In recent years, scientists have built various atlases, which are databases that define cells and tissues based on their gene expression patterns. The amount of data on tens of thousands of genes for hundreds of millions of cells - from many species - is staggering.
The chief medical officer and the CEO of Flagler Health discuss how their company is developing artificial intelligence tools for a specialty that has long been underserved by technology.
